Let your IDE call other models, not just write code.

What is CALL MODEL?

Your IDE assistant may write code and organize requirements, but its current model may not generate images, video or audio. CALL MODEL adds a separate execution path: your assistant organizes a task, then calls the external model you specify. It does not replace the IDE's main model or add a separate chat app.

Text: writing, rewriting or analysis suited to the chosen model.
Images: generation or supported editing, with reference-image support determined by the model.
Video: submit generation tasks and query their original task IDs.
Audio: supported speech or audio tasks according to the model contract.

Why a Skill instead of one sentence?

A Skill is reusable operating guidance, not another AI model. A request like ‘make an image’ does not tell an IDE where the connection is, how to call an exact model or how to poll an asynchronous task. The Skill supplies that method. The host still needs file access and secure HTTP execution; the Skill does not create permissions the host lacks.

Copy the prompt into your IDE.

This is the full installation guide, not a model task. Give it to a Skill-capable IDE or agent.

IDE installation prompt (full text)

---
name: call-model
description: Use the INT-AI V6 client's CALL MODEL connection from an IDE or Agent to call an exact model name for text, image, video, audio and other supported generation tasks.
---

# CALL MODEL

CALL MODEL is a client-assisted direct HTTP connection for non-Codex IDEs. It
does not use MCP, local MCP processes, plugins, connectors, or model catalogs.

## Install the Skill

Use the host's native Skill loader to actually install and enable this Skill.
Do not merely read or summarize it. Use:
`https://raw.githubusercontent.com/passion0501/CALL-MODEL/main/skills/call-model/SKILL.md`

If the host cannot persist a Skill, stop and ask the user to create/enable it.
Do not execute a model request until the host confirms it is loaded.

After the Skill is enabled, follow its own first-use instructions for Client V6,
account balance and API Key. Never search for, install, start, or call MCP tools
for this workflow.

## Connection

Before a model request, check the client-maintained file:
`%LOCALAPPDATA%\INTClientV6\call-model\connection.json`.

If the file is missing or invalid, return exactly:

`CALL MODEL 需要 INT-AI Client V6。当前未发现可用连接文件。是否同意现在执行 https://clientdownload.intai.cc/install.ps1 安装客户端？`

Only after an explicit user agreement may the host execute that installer. Do
not execute the model task in the same turn. After installation, ask the user
to start the client and complete the account steps above.

If the file exists but has no usable `api_key`, return exactly:

`请启动 INT-AI Client V6，完成注册/登录、充值（如需付费模型）并创建或选择主密钥，然后重试 CALL MODEL。`

Use `api_key` only as the HTTP `Authorization: Bearer ...` header. Never place
it in prompt text, JSON body, tool arguments, shell scripts, URLs, logs, or a
reply. If the host cannot keep the header separate from model-visible text,
stop and report that the host cannot perform a safe CALL MODEL request.

## Trigger and execution

Require the user's complete exact model name. Prefer:

`@CALL MODEL`

`使用 CALL MODEL <精准模型名> <任务提示词>`

Example: `使用 CALL MODEL GPT-IMAGE-2.5-4K，生成一张都市夜景的图。`

Use only the user's complete exact model name. Do not list, recommend, rename,
substitute or downgrade a model. Preserve the exact model name and request
fields. If a task was accepted, timed out, disconnected, or has uncertain
acceptance, query the existing task when possible and never submit it again
automatically.

If clipboard access fails, select and copy the text manually. The prompt matches the project's public installation guide. Open plain text

Prepare the client, account and key

Start INT-AI Client, sign in and select a valid API key. Paid models require enough balance. The client maintains the connection file, so you do not paste keys into chat. Your IDE must actually support installing and enabling Skills and making secure requests.

Your first task after installation

Give the full prompt above to your IDE and confirm the Skill is enabled, not merely read. Copy a complete model name from Model Plaza and state your task and assets.

Example: Use CALL MODEL <exact image model> to generate a poster from this brief.
Example: Use CALL MODEL <exact speech model> to generate audio from this narration.
Angle brackets are placeholders, not actual model names. Input and output formats depend on the model.
Query accepted tasks by their original ID; do not resubmit automatically after timeouts or uncertain outcomes.

How is it different from API access or AI SHOP?

CALL MODEL is a way to use model services from an IDE. Developers may instead write direct API calls. AI SHOP sells account, subscription and top-up products; buying an application membership does not give you INT-AI API balance or free CALL MODEL usage.

Charges and compatibility

The public Skill has no separate tool fee. Model calls follow current pricing and account permissions, with units varying by model. Not every IDE has the required capabilities, and not every model accepts every input.

Questions & answers

Does installing unlock free access to every model?

No. The Skill provides operating instructions; model usage follows platform pricing.

Does it replace my IDE login or main model?

No. It is an additional external-model path, not a requirement to change your IDE's main login.

What if the client is missing?

The Skill guides you to prepare the client connection. Installation requires user consent.

Do I need MCP?

No. Current CALL MODEL uses the client connection file and direct HTTPS calls.